Factorial Experiments with Minimum Changes in Run Sequences

Abstract

Randomization of run sequences in factorial experiments may result in large number of changes in factor levels which will make the experimentation expensive, time-consuming and difficult. Experiments, in which it is difficult to change the levels of factor(s), use of run sequences with minimum changes may often be preferable to a random run sequence. Here, we have developed a general method to obtain symmetric factorial with minimum changes in run sequence along with general expression of factor-wise number of level changes. Further, minimally changed run sequences to develop half replicate of 2-level factorial experiments and 2-level factorial in which only highest order factorial effect get confounded, have also been obtained. For providing readymade solution to the end users, SAS macro have been developed for generating symmetric factorial and half replicate of 2-level factorial with minimum changes in run sequence along with its parameters.